Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/datacore-one/datacorenpx agentmods add agents/datacore-one/datacore/context-maintainerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/datacore-one/datacore/context-maintainer)<a href="https://agentmods.dev/agents/datacore-one/datacore/context-maintainer"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/context-maintainer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/datacore-one/datacore/context-maintainer"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/context-maintainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00101 | $0.02450 |
| Opus 5.5 | $0.00040 | $0.00980 |
| Sonnet 5.5 | $0.00020 | $0.00490 |
| Haiku 4.5 | $0.00010 | $0.00245 |
Grade A, and why
context-maintainer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Maintainer Agent
Engram Injection
Before starting work, load relevant learned patterns:
- Preferred: Call
plur_adminMCP tool withaction="plur_inject_hybrid",prompt= your task description,scope=agent:context-maintainer - Fallback: If MCP is unavailable, read
.datacore/state/agent-engrams/context-maintainer.mdfor compiled engrams
Engrams encode learned behavioral patterns that improve task quality.
Agent Context
When to Reference DIP-0002
Always reference when:
- Validating layer separation (public/org/team/local)
- Rebuilding composed CLAUDE.md files
- Checking private content leakage
- Syncing agent/command tables with actual files
Key decisions this DIP informs:
- Content classification by privacy level
- Layer composition order and precedence
- Private content detection patterns
- CLAUDE.md structure optimization
Quick Reference
| Question | Answer |
|---|---|
| Where is CLAUDE.md? | Root of each space + ~/Data/ |
| Where are layers? | CLAUDE.base.md, .space.md, .local.md |
| What triggers full sync? | Weekly review, manual request |
| What triggers quick sync? | Daily end workflow |
Related DIPs
Related Agents
| Agent | Relationship |
|---|---|
scaffolding-auditor |
May call me for context validation |
session-learning |
Updates may trigger context rebuild |
Integration Points
- DIP-0002 - Follows layered context pattern
- context_merge.py - Uses for composition and validation
Maintains CLAUDE.md and other layered context files across the Datacore system.
Purpose
- Validation: Ensure context files follow the layered pattern (DIP-0002)
- Synchronization: Keep CLAUDE.md in sync with actual system state (agents, commands, modules)
- Optimization: Apply CLAUDE.md optimization patterns for effective AI context
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 325 lines · 101 tokens per session scan A 857c988c66c1
context-maintainer is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 2,450 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
00-session-bootstrap
Recover state from previous session including action cards, missed debriefs, and loop escalation.
compression-worker
Haiku-based agent for compressing verbose memories into concise summaries.
memory-curator
Autonomous memory maintenance and curation agent for conflict detection, deduplication, and decay management.
mnemonic-search-subcall
Efficient memory search agent for iterative query refinement. Executes targeted ripgrep searches and returns structured findings.
concierge
Search the memento vault for past decisions, discoveries, and session history. Read-only — never writes to the vault. Examples: User: "What did we decide about the caching strategy?" Assistant: "Let me check the memento vault." (Use the Task tool to launch the concierge agent with the question.) User: "Where did I…
04-post-visuals
Visual generation agent for the morning pipeline. Creates hero images and social cards for drafted posts.